Search results

The purpose of this paper is to achieve accurate integrated navigation results for the unmanned aerial vehicle (UAV) systems even in the presence of possible navigation faults in the subsystems of the federated Kalman filter.

The federated Kalman filter is modified from two aspects to get accurate navigation results under abnormity. First, time-variant vector distribution coefficients trading off the navigation accuracy and the observability degree of each state component are computed to replace the traditional scalar coefficients. Second, a fault-tolerant filter is proposed as the local navigation filter.

Simulations for the navigation of a UAV system show that the proposed method can be applied for accurate navigation purpose even in the presence of subsystem navigation faults.

New fault-tolerant federated Kalman filters for integrated navigation are presented to achieve accurate navigation solutions.

The federated filter created by Carlson has been widely used in multi-sensor integrated navigation. Compared with no-reset federated filter, the reset mode has greater sub-filters’ performance, but faults of any subsystem would affect other healthy subsystems via global fusion and the sub-optimality of sub-filters’ estimation has influence on fault detection sensitivity. It’s a challenge to design a robust reset federated filter.

The time-varying observation noise is designed to reduce proportions of observation information in faulty sub-filters. A new dynamic information distribution algorithm based on optimal residual chi-square detection function is presented to reduce proportions of faulty sub-filters’ estimation in information fusion filter.

The robust filtering algorithm represents a filtering strategy for reset federated filter. Compared with fault isolation, the navigation result is smoother by using this algorithm. It has significant benefits in avoiding faulty sensors’ contamination and the performance of federated filter is greatly improved.

The approach described in this paper provides a new method to deal with federated reset filter’s faulty problems. This new robust federated filter algorithm possesses a great potential for various applications.

The approach described in this paper can be used in multi-sensor integrated navigation with no fewer than three sensors.

Compared with conventional approach of fault isolation, the proposed algorithm does not destroy the continuity and integrity of the filtering process. It improves the performance of the federated filter by reducing proportions of faulty observation information. It also reduces the influence of sub-optimality on fault detection sensitivity.

The Embedded GPS/INS System (EGI) has been used more widely as central navigation equipment of aircraft. For certain cases needing high attitude accuracy, star sensor can be integrated with EGI to improve attitude performance. Since the filtering‐correction loop has already built in finished EGI product, centralized or federated Kalman filter is not applicable for integrating EGI with star sensor; it is a challenge to design multi‐sensor information fusion algorithm suitable for this situation. The purpose of this paper is to present a double‐layer fusion scheme and algorithms to meet the practical need of constructing integrated multi‐sensor navigation system by star sensor assisting finished EGI unit.

The alternate fusion algorithms for asynchronous measurements and the sequential fusion algorithms for synchronous measurements are presented. By combining alternate filtering and sequential filtering algorithms, a kind of double‐layer fusion algorithms for multi‐sensors is proposed and validated by semi‐physical test in this paper.

The double‐layer fusion algorithms represent a filtering strategy for multiple non‐identical parallel sensors to assist INS, while the independent estimation‐correction loop in EGI is still maintained. It has significant benefits in updating original navigation system by integrating new sensors.

The approach described in this paper can be used in designing similar multi‐sensor information fusion navigation system composed by EGI and various kinds of sensors, so as to improve the navigation performance.

Compared with conventional approach, in the situation that centralized and federated Kalman filter are not applicable, the double‐layer fusion scheme and algorithms give an external filtering strategy for measurements of finished EGI unit and star sensors.

This paper aims to present a multi-source information fusion algorithm based on factor graph for autonomous underwater vehicles (AUVs) navigation and positioning to address the asynchronous and heterogeneous problem of multiple sensors.

The factor graph is formulated by joint probability distribution function (pdf) random variables. All available measurements are processed into an optimal navigation solution by the message passing algorithm in the factor graph model. To further aid high-rate navigation solutions, the equivalent inertial measurement unit (IMU) factor is introduced to replace several consecutive IMU measurements in the factor graph model.

The proposed factor graph was demonstrated both in a simulated and vehicle environment using IMU, Doppler Velocity Log, terrain-aided navigation, magnetic compass pilot and depth meter sensors. Simulation results showed that the proposed factor graph processes all available measurements into the considerably improved navigation performance, computational efficiency and complexity compared with the un-simplified factor graph and the federal Kalman filtering methods. Semi-physical experiment results also verified the robustness and effectiveness.

The proposed factor graph scheme supported a plug and play capability to easily fuse asynchronous heterogeneous measurements information in AUV navigation systems.

To improve insufficient management by artificial management, especially for traffic accidents that occur at crossroads, the purpose of this paper is to develop a pro-active warning system for crossroads at construction sites. Although prior studies have made efforts to develop warning systems for construction sites, most of them paid attention to the construction process, while the accidents that occur at crossroads were probably overlooked.

By summarizing the main reasons resulting for those accidents occurring at crossroads, a pro-active warning system that could provide six functions for countermeasures was designed. Several approaches relating to computer vision and a prediction algorithm were applied and proposed to realize the setting functions.

One 12-hour video that films a crossroad at a construction site was selected as the original data. The test results show that all designed functions could operate normally, several predicted dangerous situations could be detected and corresponding proper warnings could be given. To validate the applicability of this system, another 36-hour video data were chosen for a performance test, and the findings indicate that all applied algorithms show a significant fitness of the data.

Computer vision algorithms have been widely used in previous studies to address video data or monitoring information; however, few of them have demonstrated the high applicability of identification and classification of the different participants at construction sites. In addition, none of these studies attempted to use a dynamic prediction algorithm to predict risky events, which could provide significant information for relevant active warnings.

This paper aims to improve the performance of the autonomous optical navigation using relativistic perturbation of starlight, which is a promising technique for future space missions. Through measuring the change in inter-star angle due to the stellar aberration and the gravitational deflection of light with space-based optical instruments, the position and velocity vectors of the spacecraft can be estimated iteratively.

To enhance the navigation performance, an integrated optical navigation (ION) method based on the fusion of both the inter-star angle and the inter-satellite line-of-sight measurements is presented. A Q-learning extended Kalman filter (QLEKF) is designed to optimize the state estimate.

Simulations illustrate that the integrated optical navigation outperforms the existing method using only inter-star angle measurement. Moreover, the QLEKF is superior to the traditional extended Kalman filter in navigation accuracy.

A novel ION method is presented, and an effective QLEKF algorithm is designed for information fusion.

At present, smartphones are embedded with accelerometers, gyroscopes, magnetometers and WiFi sensors. Most researchers have delved into the use of these sensors for localization. However, there are still many problems in reducing fingerprint mismatching and fusing these positioning data. The purpose of this paper is to improve positioning accuracy by reducing fingerprint mismatching and designing a weighted fusion algorithm.

For the problem of magnetic mismatching caused by singularity fingerprint, derivative Euclidean distance uses adjacent fingerprints to eliminate the influence of singularity fingerprint. To improve the positioning accuracy and robustness of the indoor navigation system, a weighted extended Kalman filter uses a weighted factor to fuse multisensor data.

The scenes of the teaching building, study room and office building are selected to collect data to test the algorithm’s performance. Experiments show that the average positioning accuracies of the teaching building, study room and office building are 1.41 m, 1.17 m, and 1.77 m, respectively.

The algorithm proposed in this paper effectively reduces fingerprint mismatching and improve positioning accuracy by adding a weighted factor. It provides a feasible solution for indoor positioning.

The paper proposes a privacy-preserving artificial intelligence-enabled video surveillance technology to monitor social distancing in public spaces.

The paper proposes a new Responsible Artificial Intelligence Implementation Framework to guide the proposed solution's design and development. It defines responsible artificial intelligence criteria that the solution needs to meet and provides checklists to enforce the criteria throughout the process. To preserve data privacy, the proposed system incorporates a federated learning approach to allow computation performed on edge devices to limit sensitive and identifiable data movement and eliminate the dependency of cloud computing at a central server.

The proposed system is evaluated through a case study of monitoring social distancing at an airport. The results discuss how the system can fully address the case study's requirements in terms of its reliability, its usefulness when deployed to the airport's cameras, and its compliance with responsible artificial intelligence.

The paper makes three contributions. First, it proposes a real-time social distancing breach detection system on edge that extends from a combination of cutting-edge people detection and tracking algorithms to achieve robust performance. Second, it proposes a design approach to develop responsible artificial intelligence in video surveillance contexts. Third, it presents results and discussion from a comprehensive evaluation in the context of a case study at an airport to demonstrate the proposed system's robust performance and practical usefulness.

In this study, Integrated Air Data – Doppler Navigation System is developed and presented. Air Data System and Doppler Radar have different advantages and disadvantages in applications in flight control and navigation systems. The reason of this integration is to achieve the best combination of the features and eliminate the disadvantages of these systems. As a consequence of this integration via Kalman filtering, an integrated navigation system with high accuracy of airvehicle velocity and position and with high measurement frequency is attained. On basis of this integrated system, the possibility to estimate accurate and real time inflight wind speed is explained.

Localization of the nodes is crucial for gaining access of different nodes which would provision in extreme areas where networks are unreachable. The feature of localization of nodes has become a significant study where multiple features on distance model are implicated on predictive and heuristic model for each set of localization parameters that govern the design on energy minimization with proposed adaptive threshold gradient feature (ATGF) model. A received signal strength indicator (RSSI) model with node estimated features is implicated with localization problem and enhanced with hybrid cumulative approach (HCA) algorithm for node optimizations with distance predicting.

Using a theoretical or empirical signal propagation model, the RSSI (known transmitting power) is converted to distance, the received power (measured at the receiving node) is converted to distance and the distance is converted to RSSI (known receiving power). As a result, the approximate distance between the transceiver node and the receiver may be determined by measuring the intensity of the received signal. After acquiring information on the distance between the anchor node and the unknown node, the location of the unknown node may be determined using either the trilateral technique or the maximum probability estimate approach, depending on the circumstances using federated learning.

Improvisation of localization for wireless sensor network has become one of the prime design features for estimating the different conditional changes externally and internally. One such feature of improvement is observed in this paper, via HCA where each feature of localization is depicted with machine learning algorithms imparting the energy reduction problem for each newer localized nodes in Section 5. All affected parametric features on energy levels and localization problem for newer and extinct nodes are implicated with hybrid cumulative approach as in Section 4. The proposed algorithm (HCA with AGTF) has implicated with significant change in energy levels of nodes which are generated newly and which are non-active for a stipulated time which are mentioned and tabulated in figures and tables in Section 6.

Localization of the nodes is crucial for gaining access of different nodes which would provision in extreme areas where networks are unreachable. The feature of localization of nodes has become a significant study where multiple features on distance model are implicated on predictive and heuristic model for each set of localization parameters that govern the design on energy minimization with proposed ATGF model. An RSSI model with node estimated features is implicated with localization problem and enhanced with HCA algorithm for node optimizations with distance predicting.